{"adoption": {"forks": 117, "observed_at": "2026-08-28T04:03:34.052780+00:00", "stars": 1095}, "canonical_url": "https://ross.abutalabs.com/products/cuda_kernel_samples", "card": {"archived": false, "artifact_type": "learning-resource", "description": "CUDA 算子手撕与面试指南", "domain": ["gpu-computing", "machine-learning", "tutorials", "education"], "enriched": true, "function": ["gpu-computing", "developer-tools", "benchmarking"], "health_score": 43, "homepage": null, "language": "Cuda", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Tongkaio/CUDA_Kernel_Samples"], "name": "Tongkaio/CUDA_Kernel_Samples", "platform": ["cpp", "cross-platform"], "pushed_at": "2025-08-23T14:14:00+00:00", "repo": "Tongkaio/CUDA_Kernel_Samples", "stars": 1095, "tags": ["cuda", "gpu-kernels", "interview-preparation", "performance-optimization", "sgemm", "reduction", "deep-learning-operators", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["prepare for CUDA kernel interview questions", "learn to write optimized sgemm kernels", "study reduction and softmax kernel optimization", "understand vectorized memory access with float4", "learn how to avoid bank conflicts in transpose kernels", "practice writing CUDA operators from naive to optimized versions"], "what_it_is": "A curated collection of hand-written CUDA kernel samples covering common operators like elementwise add, reduction, softmax, sgemm, and transpose, with naive and optimized implementations. It serves as an interview preparation guide for CUDA programming, pairing each operator with GPU architecture knowledge points and optimization strategies.", "when_to_avoid": ["you need a production-ready CUDA operator library like cuBLAS or CUTLASS", "you are looking for a general CUDA tutorial rather than operator-focused interview prep", "you need kernels for domains beyond the covered operators (e.g., convolutions, attention)"], "when_to_choose": ["you are preparing for GPU/CUDA programming interviews", "you want annotated, progressive examples of kernel optimization techniques", "you need a quick reference for common CUDA operator implementations"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cuda_kernel_samples", "repo": "Tongkaio/CUDA_Kernel_Samples", "role": "main", "score": 42}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.052780+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:47:14.163718+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a3a00a116360263b1b7577b419e269e15ede8b71d6e1c553ee08a687db025398", "fetched_at": "2026-08-28T04:03:34.052780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tongkaio/CUDA_Kernel_Samples"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 38, "longevity": 61, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 855, "days_push": 375, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 42, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}